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

    Neuronpedia

    INDEX
    Explanations

    software issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agma
    -0.07
    �
    -0.07
    .position
    -0.06
     inset
    -0.06
     Vall
    -0.06
     Degrees
    -0.06
     Petra
    -0.06
    item
    -0.06
    explode
    -0.06
     learning
    -0.06
    POSITIVE LOGITS
    Ford
    0.07
     woke
    0.06
    ğında
    0.06
     był
    0.06
     lékař
    0.06
    woke
    0.06
    odigo
    0.06
     resignation
    0.06
    translations
    0.06
    overwrite
    0.06
    Act Density 0.470%

    No Known Activations