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

    Neuronpedia

    INDEX
    Explanations

    Expressing an opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iagnostics
    -0.07
    ']>;↵
    -0.06
     Frances
    -0.06
     Films
    -0.06
    ADING
    -0.06
    995
    -0.06
    icons
    -0.06
    /videos
    -0.05
     melt
    -0.05
    ायत
    -0.05
    POSITIVE LOGITS
     참가
    0.07
     Geç
    0.07
    bee
    0.07
    opro
    0.06
    応
    0.06
    лоч
    0.06
     («
    0.06
    ------------------------------------------------------------------------------------------------
    0.06
     вже
    0.06
     veterin
    0.06
    Act Density 0.041%

    No Known Activations