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

    Neuronpedia

    INDEX
    Explanations

    concept

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .targets
    -0.07
    요일
    -0.07
    とう
    -0.06
    .jobs
    -0.06
    هـ
    -0.06
    slave
    -0.06
    _damage
    -0.06
    Bộ
    -0.06
    Optimizer
    -0.06
     нічого
    -0.06
    POSITIVE LOGITS
     incidents
    0.06
     duplic
    0.06
     FIR
    0.06
     colourful
    0.06
     mechanics
    0.06
    ApiModelProperty
    0.06
     Survey
    0.06
    ':['
    0.06
     accurate
    0.06
     Bulgaria
    0.06
    Act Density 0.079%

    No Known Activations