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

    Neuronpedia

    INDEX
    Explanations

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vals
    -0.07
    	z
    -0.06
    리즈
    -0.06
    aming
    -0.06
     يجب
    -0.06
     digging
    -0.06
     vững
    -0.06
    روس
    -0.06
    �
    -0.06
     anth
    -0.06
    POSITIVE LOGITS
     mongoose
    0.07
     overst
    0.06
    LOS
    0.06
    .SEVER
    0.06
    _SOURCE
    0.06
    �
    0.06
    @NoArgsConstructor
    0.06
    IONS
    0.06
     keeps
    0.06
    -pay
    0.06
    Act Density 0.003%

    No Known Activations