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

    Neuronpedia

    INDEX
    Explanations

    definitions of terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _basis
    -0.06
     herpes
    -0.06
     ');
↵
    -0.06
    ιας
    -0.06
     ポ
    -0.06
     Manuel
    -0.06
     Carl
    -0.06
     além
    -0.06
    _SPELL
    -0.06
    „V
    -0.06
    POSITIVE LOGITS
    .iv
    0.07
    ็็
    0.07
    akit
    0.06
    .warning
    0.06
    _wrong
    0.06
    armac
    0.06
    ozor
    0.06
    .Exit
    0.06
    _BOTH
    0.06
     waving
    0.06
    Act Density 0.036%

    No Known Activations