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

    Neuronpedia

    INDEX
    Explanations

    file directories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cap
    -0.07
    .getChannel
    -0.07
    zet
    -0.07
    achines
    -0.06
    .IsActive
    -0.06
    code
    -0.06
     گیرد
    -0.06
     EZ
    -0.06
    �습니다
    -0.06
     Nz
    -0.06
    POSITIVE LOGITS
     Tools
    0.06
     standards
    0.06
     bombed
    0.06
     dedication
    0.06
    -prepend
    0.06
     вок
    0.06
     selections
    0.06
     penalties
    0.06
     replaced
    0.06
     shouts
    0.06
    Act Density 0.021%

    No Known Activations