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

    Neuronpedia

    INDEX
    Explanations

    dialog

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🏯
    -0.07
    📒
    -0.07
     svn
    -0.06
    etable
    -0.06
     Van
    -0.06
     Con
    -0.06
    唱
    -0.06
     sponsorship
    -0.06
     Logistic
    -0.06
    ripe
    -0.06
    POSITIVE LOGITS
     funct
    0.07
     curing
    0.07
     ost
    0.07
     inspect
    0.07
     seab
    0.07
     actual
    0.07
    Ố
    0.06
    _Reg
    0.06
    عق
    0.06
     occurs
    0.06
    Act Density 0.000%

    No Known Activations