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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gujarat
    -0.07
    ]-'
    -0.07
    届
    -0.06
     char
    -0.06
    찌
    -0.06
    “These
    -0.06
     cliffs
    -0.06
    “They
    -0.06
    senha
    -0.06
    Ka
    -0.06
    POSITIVE LOGITS
    %,
    0.07
     připrav
    0.07
     школи
    0.07
     acoustic
    0.07
     čtyři
    0.07
     пре
    0.06
     mari
    0.06
     část
    0.06
     Provision
    0.06
    _por
    0.06
    Act Density 0.012%

    No Known Activations