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

    Neuronpedia

    INDEX
    Explanations

    generated responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Volumes
    0.42
     Items
    0.40
     hypothesize
    0.38
     Objects
    0.38
    igle
    0.38
     ولكن
    0.37
    公司的
    0.37
     butane
    0.37
     Accounts
    0.36
     Pages
    0.36
    POSITIVE LOGITS
     [{
    0.45
    Hawaii
    0.45
    [$
    0.44
    [],
    0.44
    ["
    0.42
     indiscriminate
    0.41
     [$
    0.39
    Wrapped
    0.38
     pou
    0.38
     [...
    0.38
    Act Density 0.000%

    No Known Activations