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

    Neuronpedia

    INDEX
    Explanations

    work/task completion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     declaring
    -0.06
     Pir
    -0.06
     Καρ
    -0.06
    Been
    -0.06
     عليه
    -0.06
    цеп
    -0.06
     <?=
    -0.06
    вин
    -0.06
    尚
    -0.06
    POSITIVE LOGITS
    hint
    0.07
    zent
    0.07
    .Warn
    0.06
     hairst
    0.06
     strained
    0.06
    aaaa
    0.06
    فات
    0.06
    entine
    0.06
     mutableListOf
    0.06
    DSP
    0.06
    Act Density 0.370%

    No Known Activations