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

    Neuronpedia

    INDEX
    Explanations

    token

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    3
    -0.09
    4
    -0.09
    883
    -0.08
     Grey
    -0.08
     Guide
    -0.08
    323
    -0.08
    55
    -0.07
    isbury
    -0.07
     house
    -0.07
     canvas
    -0.07
    POSITIVE LOGITS
     token
    0.13
    Token
    0.13
    token
    0.13
     Token
    0.12
    /token
    0.10
    Tokens
    0.10
    	token
    0.09
     Tok
    0.09
     TokenType
    0.09
    .Token
    0.09
    Act Density 0.014%

    No Known Activations