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

    Neuronpedia

    INDEX
    Explanations

    At

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Never
    -0.06
    алу
    -0.06
    umni
    -0.06
    ربع
    -0.06
     slander
    -0.06
    нина
    -0.06
    ный
    -0.06
     era
    -0.06
    _login
    -0.06
     Haley
    -0.06
    POSITIVE LOGITS
     $#
    0.07
    MaxLength
    0.07
     Clause
    0.07
     cheap
    0.07
    iteDatabase
    0.06
     davidjl
    0.06
     Blur
    0.06
     drill
    0.06
     arriv
    0.06
    _OPCODE
    0.06
    Act Density 0.004%

    No Known Activations