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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /MM
    -0.07
     Sham
    -0.07
     ARG
    -0.06
     Mason
    -0.06
    <W
    -0.06
    ADM
    -0.06
     glo
    -0.06
     शर
    -0.06
     META
    -0.06
     SW
    -0.06
    POSITIVE LOGITS
    ManagedObjectContext
    0.07
    itura
    0.07
    �
    0.06
    τιν
    0.06
    suspend
    0.06
    ，默认
    0.06
    creds
    0.06
    reb
    0.06
     weave
    0.06
     Δεν
    0.06
    Act Density 0.000%

    No Known Activations