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

    Neuronpedia

    INDEX
    Explanations

    APE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .describe
    -0.07
     Ladies
    -0.07
    Proc
    -0.07
    -bre
    -0.06
    name
    -0.06
    Helper
    -0.06
    ripp
    -0.06
    amous
    -0.06
     lamp
    -0.06
    เหล
    -0.06
    POSITIVE LOGITS
     عضو
    0.06
     Oliver
    0.06
     Alex
    0.06
     awakened
    0.06
     infringement
    0.06
     リ
    0.06
     insn
    0.06
     residing
    0.06
    Aj
    0.06
     ABI
    0.06
    Act Density 0.003%

    No Known Activations