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

    Neuronpedia

    INDEX
    Explanations

    Code and random text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bald
    -0.07
     mó
    -0.06
     replaced
    -0.06
     Pass
    -0.06
    .describe
    -0.06
    addAll
    -0.06
    jal
    -0.06
    master
    -0.06
     Magnetic
    -0.06
    cdot
    -0.06
    POSITIVE LOGITS
     önceki
    0.07
    iology
    0.06
     eighteen
    0.06
     آزمایش
    0.06
     UF
    0.06
     hormonal
    0.06
     PIXEL
    0.06
        
    0.06
    rschein
    0.06
    (policy
    0.06
    Act Density 0.004%

    No Known Activations