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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases for unique items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।
    0.48
    sensitive
    0.48
    appoint
    0.48
    asti
    0.47
    חס
    0.46
    ‌اند
    0.45
    anim
    0.44
    }=$
    0.44
    whole
    0.43
    bar
    0.43
    POSITIVE LOGITS
     DEV
    0.49
     Vieni
    0.48
     MODELS
    0.48
     groupId
    0.48
     DEVICE
    0.47
     IDF
    0.47
     SLASH
    0.46
     segí
    0.46
     stammt
    0.46
     Ceremony
    0.45
    Act Density 0.000%

    No Known Activations