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

    Neuronpedia

    INDEX
    Explanations

    visible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hoe
    -0.07
    love
    -0.07
    _digest
    -0.07
    vertices
    -0.07
     textSize
    -0.07
    _VALUE
    -0.07
     susceptible
    -0.07
    }));↵
    -0.07
    ϝ
    -0.07
    '))↵↵↵
    -0.07
    POSITIVE LOGITS
    いら
    0.08
     ocup
    0.08
     acted
    0.07
     될
    0.07
    ⓟ
    0.07
    @login
    0.06
     być
    0.06
     squad
    0.06
    .uf
    0.06
    .Prop
    0.06
    Act Density 0.003%

    No Known Activations