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

    Neuronpedia

    INDEX
    Explanations

    follow `-->`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    树
    0.47
     stup
    0.42
     trees
    0.41
     drzew
    0.41
     Trees
    0.41
     lex
    0.40
    сур
    0.39
     Humans
    0.38
     Tokens
    0.38
     Pogis
    0.38
    POSITIVE LOGITS
    opt
    0.49
     opt
    0.49
    optional
    0.47
    Reference
    0.46
    reference
    0.45
    factor
    0.44
     optional
    0.44
     optionally
    0.44
    Opt
    0.43
     factor
    0.43
    Act Density 0.010%

    No Known Activations