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

    Neuronpedia

    INDEX
    Explanations

    Offering, needing, or giving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bones
    -0.07
    逃脱
    -0.07
     Angela
    -0.07
     stom
    -0.07
     Solution
    -0.07
     canActivate
    -0.07
     Decompiled
    -0.07
    eway
    -0.07
     Julien
    -0.07
     noveller
    -0.06
    POSITIVE LOGITS
    叕
    0.07
    �
    0.07
    pra
    0.07
    ┚
    0.06
    �
    0.06
     earned
    0.06
    Не
    0.06
     �
    0.06
    .").
    0.06
    龊
    0.06
    Act Density 0.117%

    No Known Activations