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

    Neuronpedia

    INDEX
    Explanations

    hard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANNER
    -0.07
    大会
    -0.07
    False
    -0.07
    กระท
    -0.06
    ád
    -0.06
     Reach
    -0.06
    high
    -0.06
    enk
    -0.06
     Lopez
    -0.06
    ).'
    -0.06
    POSITIVE LOGITS
     unitOfWork
    0.07
    >Returns
    0.07
    une
    0.06
    ilarity
    0.06
     Include
    0.06
    .BigDecimal
    0.06
    票
    0.06
     INSTALL
    0.06
     hilarious
    0.06
     Projekt
    0.06
    Act Density 0.020%

    No Known Activations