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

    Neuronpedia

    INDEX
    Explanations

    200 or 201

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ….↵↵
    -0.06
     radians
    -0.06
    Azure
    -0.06
    _CERT
    -0.06
    ior
    -0.06
    .ms
    -0.06
     MAD
    -0.06
    [tag
    -0.06
    -going
    -0.06
    _example
    -0.06
    POSITIVE LOGITS
     đầy
    0.07
    >%
    0.07
     overhe
    0.06
     codecs
    0.06
     somew
    0.06
    _due
    0.06
    
    0.06
     Jugend
    0.06
    ooks
    0.06
    _weapon
    0.06
    Act Density 0.005%

    No Known Activations