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

    Neuronpedia

    INDEX
    Explanations

    rate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Enter
    -0.07
    _resolve
    -0.07
     insistence
    -0.07
    	bit
    -0.07
    Enter
    -0.07
    inar
    -0.06
     subpoena
    -0.06
     boiled
    -0.06
     affidavit
    -0.06
    ivan
    -0.06
    POSITIVE LOGITS
     též
    0.06
    though
    0.06
    ании
    0.06
    ssue
    0.06
    ngr
    0.06
    ENDER
    0.06
    _streams
    0.06
    怕
    0.06
    "indices
    0.06
    .defaultProps
    0.06
    Act Density 0.060%

    No Known Activations