Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    action verbs associated with rolling or spinning movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    rotation or rolling

    np_acts-logits-general · gemini-2.0-flash

    rolling and rotating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <
    -0.38
    3
    -0.37
     väh
    -0.36
     nær
    -0.36
    <td>
    -0.33
     than
    -0.31
     mínimo
    -0.31
    7
    -0.31
     لمن
    -0.31
    ælp
    -0.31
    POSITIVE LOGITS
     ROLL
    0.91
    croll
    0.84
     roll
    0.84
     rolling
    0.83
     rollover
    0.83
     rotate
    0.82
     rollback
    0.81
     Rolling
    0.80
    Rolling
    0.78
     Roll
    0.77
    Act Density 0.320%

    No Known Activations