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

    Neuronpedia

    INDEX
    Explanations

    learn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    andr
    -0.07
    elay
    -0.07
    �
    -0.07
    venile
    -0.07
    Vel
    -0.07
    icl
    -0.06
    uhl
    -0.06
     Kohana
    -0.06
    umnos
    -0.06
     taller
    -0.06
    POSITIVE LOGITS
    .et
    0.07
     microbi
    0.07
     judgement
    0.07
    731
    0.06
     wag
    0.06
    _variant
    0.06
    prompt
    0.06
     FW
    0.06
    ●●●●
    0.06
     gathering
    0.06
    Act Density 0.028%

    No Known Activations