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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    collector
    -0.07
    .role
    -0.07
     FRE
    -0.07
    )),
↵
    -0.06
     mcc
    -0.06
     pedestal
    -0.06
     링크
    -0.06
     CONTEXT
    -0.06
     BIN
    -0.06
     đương
    -0.06
    POSITIVE LOGITS
     Ging
    0.07
     humanitarian
    0.06
    оят
    0.06
    omm
    0.06
    نسان
    0.06
    .PO
    0.06
    ──
    0.06
     vows
    0.06
     Σε
    0.06
    sez
    0.06
    Act Density 0.010%

    No Known Activations