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

    Neuronpedia

    INDEX
    Explanations

    sides

    np_max-act · gemini-2.0-flash

    This neuron remains inactive on every token in these examples—it doesn’t detect any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _avg
    -0.08
     Snow
    -0.06
    802
    -0.06
     Election
    -0.06
    -Le
    -0.06
     unreliable
    -0.06
    ]=="
    -0.06
     Berlin
    -0.06
    临
    -0.06
    -fold
    -0.06
    POSITIVE LOGITS
     numerator
    0.08
    prit
    0.07
    rhs
    0.07
     rhs
    0.07
     RHS
    0.07
     lhs
    0.06
     thoughtful
    0.06
     SqlDbType
    0.06
     daemon
    0.06
     writeln
    0.06
    Act Density 0.005%

    No Known Activations