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

    Neuronpedia

    INDEX
    Explanations

    Programming/coding context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     condemn
    -0.08
     flowers
    -0.07
    .CASCADE
    -0.07
    cu
    -0.07
     року
    -0.06
    ,color
    -0.06
    getState
    -0.06
    Psi
    -0.06
     four
    -0.06
    messages
    -0.06
    POSITIVE LOGITS
     Energ
    0.07
     LIVE
    0.06
    UNCH
    0.06
     ří
    0.06
    CLEAR
    0.06
    �
    0.06
     récup
    0.06
    ตะ
    0.06
    vanized
    0.06
    IMO
    0.06
    Act Density 0.067%

    No Known Activations