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

    Neuronpedia

    INDEX
    Explanations

    Installation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хто
    -0.07
    ’den
    -0.07
    坂
    -0.06
    nnen
    -0.06
    根
    -0.06
    として
    -0.06
    Toyota
    -0.06
    scala
    -0.06
     plais
    -0.06
    関係
    -0.06
    POSITIVE LOGITS
    _cm
    0.07
    	Json
    0.07
    Copy
    0.06
     Nem
    0.06
     neat
    0.06
    OCK
    0.06
    _properties
    0.06
    _buffer
    0.06
     getPassword
    0.06
     tourist
    0.06
    Act Density 0.008%

    No Known Activations