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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     esposa
    -0.07
     folks
    -0.07
     progression
    -0.07
     twentieth
    -0.07
     progressing
    -0.07
    ΟΝ
    -0.07
    wo
    -0.06
     kavram
    -0.06
    OMB
    -0.06
     algunos
    -0.06
    POSITIVE LOGITS
     at
    0.07
    ��이
    0.06
    πέ
    0.06
     件
    0.06
    .Act
    0.06
    utivo
    0.06
     Adjust
    0.05
    -holder
    0.05
    @\
    0.05
    bec
    0.05
    Act Density 0.044%

    No Known Activations