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

    Neuronpedia

    INDEX
    Explanations

    survival

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sail
    -1.26
    Sail
    -1.24
     sailing
    -1.13
     Sail
    -1.13
    sail
    -1.06
     survival
    -1.02
    bootstrapcdn
    -1.01
     Roskov
    -1.01
    SourceChecksum
    -0.97
    survival
    -0.96
    POSITIVE LOGITS
     O
    0.60
    ,
    0.53
     Ar
    0.52
     ne
    0.51
    .
    0.51
     
    0.49
     Ex
    0.48
     Ne
    0.48
     V
    0.47
    Ex
    0.47
    Act Density 0.067%

    No Known Activations