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

    Neuronpedia

    INDEX
    Explanations

    javascript code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    掠
    -0.08
    rient
    -0.07
    ierte
    -0.07
     mañana
    -0.06
    .folder
    -0.06
     Santana
    -0.06
    vern
    -0.06
     cancel
    -0.06
     Sierra
    -0.06
    velocity
    -0.06
    POSITIVE LOGITS
    IH
    0.07
    owment
    0.07
    emphasis
    0.07
    uai
    0.07
    TM
    0.07
     spokeswoman
    0.07
    👦
    0.07
     prominently
    0.07
    多い
    0.07
     Jail
    0.07
    Act Density 0.155%

    No Known Activations