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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Planning
    -0.07
    itation
    -0.07
     reimb
    -0.07
     planning
    -0.06
     �
    -0.06
     kültür
    -0.06
    iversite
    -0.06
    cessive
    -0.06
     чи
    -0.06
    оки
    -0.06
    POSITIVE LOGITS
     Liber
    0.08
    Brit
    0.07
    xAF
    0.07
     Salah
    0.07
     Spell
    0.06
    Bo
    0.06
    rays
    0.06
    ."↵↵
    0.06
    -gr
    0.06
    TF
    0.06
    Act Density 0.049%

    No Known Activations