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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     самым
    -0.07
     behaving
    -0.06
     british
    -0.06
     brother
    -0.06
     include
    -0.06
    بری
    -0.06
     PARTIC
    -0.06
     receiving
    -0.06
    ieron
    -0.06
    enden
    -0.06
    POSITIVE LOGITS
     Propel
    0.06
    ００
    0.06
    /her
    0.06
    /he
    0.06
     �
    0.06
    /St
    0.06
    Unnamed
    0.06
    bounds
    0.06
    .tencent
    0.06
    _lua
    0.06
    Act Density 0.022%

    No Known Activations